AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation
This addresses the challenge of generating high-resolution 3D surfaces without memory constraints for applications in computer vision and graphics, though it appears incremental as it builds on existing shape generation methods.
The paper tackles the problem of generating 3D shapes by introducing AtlasNet, a method that represents shapes as parametric surface elements to infer surface representations, achieving improved precision and generalization on the ShapeNet benchmark for tasks like auto-encoding and single-view reconstruction.
We introduce a method for learning to generate the surface of 3D shapes. Our approach represents a 3D shape as a collection of parametric surface elements and, in contrast to methods generating voxel grids or point clouds, naturally infers a surface representation of the shape. Beyond its novelty, our new shape generation framework, AtlasNet, comes with significant advantages, such as improved precision and generalization capabilities, and the possibility to generate a shape of arbitrary resolution without memory issues. We demonstrate these benefits and compare to strong baselines on the ShapeNet benchmark for two applications: (i) auto-encoding shapes, and (ii) single-view reconstruction from a still image. We also provide results showing its potential for other applications, such as morphing, parametrization, super-resolution, matching, and co-segmentation.